llama-2FineTuned / checkpoint-10 /trainer_state.json
bilkultheek's picture
Initial commit
16fa3da verified
raw
history blame
1.54 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.05333333333333334,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.1764705882352942e-05,
"loss": 1.9122,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 2.3529411764705884e-05,
"loss": 2.0707,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 3.529411764705883e-05,
"loss": 1.9703,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 4.705882352941177e-05,
"loss": 2.015,
"step": 4
},
{
"epoch": 0.03,
"learning_rate": 5.882352941176471e-05,
"loss": 2.119,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 7.058823529411765e-05,
"loss": 2.0515,
"step": 6
},
{
"epoch": 0.04,
"learning_rate": 8.23529411764706e-05,
"loss": 1.7436,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 9.411764705882353e-05,
"loss": 1.9326,
"step": 8
},
{
"epoch": 0.05,
"learning_rate": 0.00010588235294117647,
"loss": 2.0819,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 0.00011764705882352942,
"loss": 1.9965,
"step": 10
}
],
"max_steps": 561,
"num_train_epochs": 3,
"total_flos": 3333258509352960.0,
"trial_name": null,
"trial_params": null
}